Optimal robust control of vehicle lateral stability using damped least-square backpropagation training of neural networks

Hamid Taghavifar; Chuan Hu; Leyla Taghavifar; Yechen Qin; Jing Na; Chongfeng Wei

doi:10.1016/j.neucom.2019.12.045

Optimal robust control of vehicle lateral stability using damped least-square backpropagation training of neural networks

Hamid Taghavifar
, Chuan Hu
, Leyla Taghavifar
, Yechen Qin
, Jing Na
, Chongfeng Wei

University of Texas at Austin
Islamic Azad University
Beijing Institute of Technology
Kunming University of Science and Technology
University of Leeds

Research output: Contribution to journal › Article › peer-review

41 Citations (Scopus)

258 Downloads (Pure)

Abstract

Chassis control systems play a significant role in achieving the desired vehicle performance and stability during various severe maneuvers. A probabilistic estimation approach by hybridization of optimal robust control and a damped least-square backpropagation based neural networks (NN) is proposed to design a control system for dealing with unknown nonlinear dynamics of a passenger car. To this end, a four-wheel active steering (4WAS) model is employed and a multilayer perceptron (ML) feed-forward backpropagation neural network (FFBPNN) model is developed as an approximator. The optimal robust control is employed to regulate the yaw rate and side-slip angle of the vehicle to follow the desired vehicle response. The developed FFBPNN model is trained to distinguish the nonlinear dynamics of the vehicle and the corresponding optimal feedback gain during a wide range of operating conditions via the state variables. The robustness of the controller is evaluated using Lyapunov stability method. The performance of the proposed controller is analyzed considering the open-loop and closed-loop responses of the nonlinear vehicle model and a sliding mode controller to track the desired yaw rate and side-slip angle responses. The results obtained during severe maneuvers suggest that the proposed control method can substantially enhance the handling and stability performances of the vehicle.

Original language	English
Pages (from-to)	256-267
Number of pages	12
Journal	Neurocomputing
Volume	384
Early online date	19 Dec 2019
DOIs	https://doi.org/10.1016/j.neucom.2019.12.045
Publication status	Published - 7 Apr 2020

Bibliographical note

NOTICE: this is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 384 (2020) DOI: 10.1016/j.neucom.2019.12.045

© 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

Funding

This work was supported by the National Science Foundation of China under Grants 61873115 and 51905028 . Hamid Taghavifar is currently an Assistant Professor with the School of Mechanical, Aerospace and Automotive Engineering, Coventry University, UK. Formerly, he was a Vehicle Ride and Handling Engineer at Fiat Chrysler ARDC, after working as a Horizon Postdoctoral Fellow at CONCAVE Research Center, Concordia University in Canada. His research focuses on automated driving, control of autonomous systems (adaptive, nonlinear, and intelligent), robotics and artificial intelligence, where he has contributed over 50 peer-reviewed papers, a book, and 2 Iranian registered patents. He serves as the Editor-in-Chief of the Journal of Advances in Vehicle Engineering, Editor for Int. J. of Vehicle Systems Modeling and Testing and Int. J. of Vehicle Information and Communication Systems. Chuan Hu is currently a Postdoctoral Fellow in the Department of Mechanical Engineering, University of Texas at Austin, Austin, USA. He was a Postdoctoral Fellow in the Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada from July 2017 to July 2018. He received the B.E. degree in vehicle engineering from Tsinghua University, Beijing, China, in 2010, the M.E. degree in vehicle operation engineering from the China Academy of Railway Sciences, Beijing, in 2013, and the Ph.D. degree in Mechanical Engineering, McMaster University, Hamilton, Canada in 2017. His research interest includes vehicle system dynamics and control, motion control and estimation of autonomous vehicles, mechatronics, robust and adaptive control. Leyla Taghavifar obtained her B.Sc. and M.Sc. degrees in Electrical Engineering from Tabriz University, and IAU of Tehran, Iran, in 2009 and 2013, respectively. Her research interests include signal processing and synchronization, telecommunications, cellular networks and artificial intelligence. Yechen Qin received the B.Sc. degree and Ph.D. degree in Mechanical Engineering from Beijing Institute of Technology, P.R. China in 2010 and 2016, respectively. He is currently working as associate professor in Beijing Institute of Technology, P.R. China. From 2013 to 2014, he was studied in Texas A&M University, US as a visiting Ph.D. student. He has also worked in Beijing Institue of Technology and University of Waterloo as postdoctoral research fellow and visiting scholar. His research interests include vehicle dynamics control and road estimation. Jing Na received the B.Eng. and Ph.D. degrees in control engineering from the School of Automation, Beijing Institute of Technology, Beijing, China, in 2004 and 2010, respectively. From 2011 to 2013, he was a Monaco/ITER Post-Doctoral Fellow with ITER Organization, Saint-Paul-l`es-Durance, France. From 2015 to 2017, he was a Marie Curie Intra-European Fellow with the Department of Mechanical Engineering, University of Bristol, Bristol, U.K. Since 2010, he has been with the Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China, where he became a Full Professor in 2013. He has co-authored one monograph published in Elsevier and authored or co-authored over 100 international journal and conference papers. His current research interests include intelligent control, adaptive parameter estimation, nonlinear control and applications for robotics, vehicle systems, and wave energy convertor. Dr. Na was a recipient of the Marie Curie Fellowship from EU, the Best Application Paper Award of the 3rd IFAC International Conference on Intelligent Control and Automation Science in 2013, and the 2017 Hsue-Shen Tsien Paper Award. He is currently an Associate Editor of Neurocomputing and has served as the IPC Chair of ICMIC in 2017. Chongfeng Wei obtained the B.Sc. degree in computational and applied mathematics and the M.Sc. degree in vehicle engineering from Southwest Jiaotong University, Chendu, China, in 2009 and 2011, respectively, and the Ph.D. degree in mechanical engineering from the University of Birmingham in 2015. After two and a half years postdoctoral research period, he joined the School of Mechanical Engineering at Shanghai Jiao Tong University as an Assistant Professor (tenure-track). He then moved to the institute of Transport Studies at University of Leeds as a research fellow in 2018. His-current research focuses on Humanlike autonomous vehicle control and collision avoidance.

Funders	Funder number
European Commission
National Natural Science Foundation of China	61873115, 51905028
National Natural Science Foundation of China

Keywords

Artificial Neural Networks
Damped Least-Square Backpropagation
Optimal Control
Vehicle Control

ASJC Scopus subject areas

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neucom.2019.12.045

Post-PrintAccepted author manuscript, 2.08 MBLicence: CC BY-NC-ND

Cite this

@article{09fdcb7995ed40ef92fd75324cc35ae8,

title = "Optimal robust control of vehicle lateral stability using damped least-square backpropagation training of neural networks",

abstract = "Chassis control systems play a significant role in achieving the desired vehicle performance and stability during various severe maneuvers. A probabilistic estimation approach by hybridization of optimal robust control and a damped least-square backpropagation based neural networks (NN) is proposed to design a control system for dealing with unknown nonlinear dynamics of a passenger car. To this end, a four-wheel active steering (4WAS) model is employed and a multilayer perceptron (ML) feed-forward backpropagation neural network (FFBPNN) model is developed as an approximator. The optimal robust control is employed to regulate the yaw rate and side-slip angle of the vehicle to follow the desired vehicle response. The developed FFBPNN model is trained to distinguish the nonlinear dynamics of the vehicle and the corresponding optimal feedback gain during a wide range of operating conditions via the state variables. The robustness of the controller is evaluated using Lyapunov stability method. The performance of the proposed controller is analyzed considering the open-loop and closed-loop responses of the nonlinear vehicle model and a sliding mode controller to track the desired yaw rate and side-slip angle responses. The results obtained during severe maneuvers suggest that the proposed control method can substantially enhance the handling and stability performances of the vehicle.",

keywords = "Artificial Neural Networks, Damped Least-Square Backpropagation, Optimal Control, Vehicle Control",

author = "Hamid Taghavifar and Chuan Hu and Leyla Taghavifar and Yechen Qin and Jing Na and Chongfeng Wei",

note = "NOTICE: this is the author{\textquoteright}s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 384 (2020) DOI: 10.1016/j.neucom.2019.12.045 {\textcopyright} 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ ",

year = "2020",

month = apr,

day = "7",

doi = "10.1016/j.neucom.2019.12.045",

language = "English",

volume = "384",

pages = "256--267",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Optimal robust control of vehicle lateral stability using damped least-square backpropagation training of neural networks

AU - Taghavifar, Hamid

AU - Hu, Chuan

AU - Taghavifar, Leyla

AU - Qin, Yechen

AU - Na, Jing

AU - Wei, Chongfeng

N1 - NOTICE: this is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 384 (2020) DOI: 10.1016/j.neucom.2019.12.045 © 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

PY - 2020/4/7

Y1 - 2020/4/7

N2 - Chassis control systems play a significant role in achieving the desired vehicle performance and stability during various severe maneuvers. A probabilistic estimation approach by hybridization of optimal robust control and a damped least-square backpropagation based neural networks (NN) is proposed to design a control system for dealing with unknown nonlinear dynamics of a passenger car. To this end, a four-wheel active steering (4WAS) model is employed and a multilayer perceptron (ML) feed-forward backpropagation neural network (FFBPNN) model is developed as an approximator. The optimal robust control is employed to regulate the yaw rate and side-slip angle of the vehicle to follow the desired vehicle response. The developed FFBPNN model is trained to distinguish the nonlinear dynamics of the vehicle and the corresponding optimal feedback gain during a wide range of operating conditions via the state variables. The robustness of the controller is evaluated using Lyapunov stability method. The performance of the proposed controller is analyzed considering the open-loop and closed-loop responses of the nonlinear vehicle model and a sliding mode controller to track the desired yaw rate and side-slip angle responses. The results obtained during severe maneuvers suggest that the proposed control method can substantially enhance the handling and stability performances of the vehicle.

AB - Chassis control systems play a significant role in achieving the desired vehicle performance and stability during various severe maneuvers. A probabilistic estimation approach by hybridization of optimal robust control and a damped least-square backpropagation based neural networks (NN) is proposed to design a control system for dealing with unknown nonlinear dynamics of a passenger car. To this end, a four-wheel active steering (4WAS) model is employed and a multilayer perceptron (ML) feed-forward backpropagation neural network (FFBPNN) model is developed as an approximator. The optimal robust control is employed to regulate the yaw rate and side-slip angle of the vehicle to follow the desired vehicle response. The developed FFBPNN model is trained to distinguish the nonlinear dynamics of the vehicle and the corresponding optimal feedback gain during a wide range of operating conditions via the state variables. The robustness of the controller is evaluated using Lyapunov stability method. The performance of the proposed controller is analyzed considering the open-loop and closed-loop responses of the nonlinear vehicle model and a sliding mode controller to track the desired yaw rate and side-slip angle responses. The results obtained during severe maneuvers suggest that the proposed control method can substantially enhance the handling and stability performances of the vehicle.

KW - Artificial Neural Networks

KW - Damped Least-Square Backpropagation

KW - Optimal Control

KW - Vehicle Control

UR - https://www.scopus.com/pages/publications/85077149766

U2 - 10.1016/j.neucom.2019.12.045

DO - 10.1016/j.neucom.2019.12.045

M3 - Article

AN - SCOPUS:85077149766

SN - 0925-2312

VL - 384

SP - 256

EP - 267

JO - Neurocomputing

JF - Neurocomputing

ER -

Optimal robust control of vehicle lateral stability using damped least-square backpropagation training of neural networks

Abstract

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this